The Agent Skills Directory

[COMMAND_EXECUTION]: The skill writes user-provided data to a file in the user's home directory (~/.devadvokit.md) as its primary function.
[PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface by saving unsanitized user input into a file that other skills are expected to read. * Ingestion points: Responses provided by the user during the guided setup interview in SKILL.md. * Boundary markers: None; the output file uses standard Markdown formatting without delimiters for untrusted content. * Capability inventory: The skill utilizes file-writing capabilities to generate the configuration file. * Sanitization: The skill does not perform validation or escaping on the user-supplied text before writing it to disk.

setup-devadvokit